Founding ML Researcher at Base Compute | Berlin, DE | Rezi

Founding ML Researcher at Base Compute

Founding ML Researcher

Base Compute · Berlin, DE

2 weeks ago

Founding ML Researcher

Base Compute · Berlin, DE

17 days ago
Resume preview

Impress employers and recruiters.
Choose from hundreds of resume examples.

Target Resume Now

About the Role

We are seeking a Founding ML Researcher to pioneer on-device AI. This role involves identifying opportunities, designing and executing experiments, and generating insights that enhance real-world performance. You will have substantial control over our research direction and influence company technical decisions.

Responsibilities

  • Identify and validate new approaches to on-device efficiency, including speculative decoding variants, novel quantization schemes, and new techniques.
  • Build intelligence systems for serving requests between on-device and frontier API models.
  • Design systems for autonomous exploration, hypothesis generation, and evaluation of research ideas to accelerate R&D.
  • Develop rigorous evaluations and benchmarks to measure real-world performance.

Requirements

  • PhD in ML or equivalent industry research experience.
  • Deep understanding of LLM architectures and AI inference principles.
  • Expertise in a relevant topic such as speculative decoding, quantization theory, model distillation, or reinforcement learning.
  • A track record of producing impactful results (research papers, open-source projects, or blog posts).
  • Strong communication skills, including the ability to explain complex ideas clearly, provide feedback, and document findings reproducibly.
  • Familiarity with GPU and accelerator architectures and kernel optimization (CUDA, ROCm, Metal, Triton, etc.).
  • Experience deploying models under on-device constraints (memory bandwidth, latency budgets, thermal and power ceilings).

Skills

  • On-device AI
  • Inference efficiency
  • Speculative decoding
  • Quantization
  • Model distillation
  • Reinforcement learning
  • LLM architectures
  • AI inference
  • GPU architectures
  • Accelerator architectures
  • Kernel optimization
  • CUDA
  • ROCm
  • Metal
  • Triton
  • Model deployment
  • Memory bandwidth optimization
  • Latency optimization
  • Written and spoken English

Location

  • Melbourne
  • Berlin

Work Type

  • In-person
  • Full-time

Experience Level

  • Founding team

Education Level

  • PhD in ML or equivalent industry research experience

Salary/Compensations

  • Strong base salary

Benefits

  • Founding team equity
  • Direct influence on technical direction
  • Opportunity to work on challenging, unsolved problems
  • Small team environment
  • Fast iteration
  • Low bureaucracy

About the Company

  • Base Compute is an AI inference lab focused on bringing AGI to devices.
  • We aim to provide fast, private, and always-available intelligence on devices.
  • We are building the infrastructure for next-generation on-device AI, from silicon optimizations to distributed inference systems.
  • We tackle complex challenges at the intersection of inference efficiency, model intelligence, and autonomous research.